运行SoccerTwos环境出错，每次prefilling到38%就报index16 is out of bounds for axis 0 with size 16
Opened this issue · 2 comments
Initialize environment begin...
load config from rls/configs/unity/env_dict.yaml successfully
[INFO] Connected to Unity environment with package version 2.1.0-exp.1 and communication version 1.5.0
Connected to Unity environment with package version 2.1.0-exp.1 and communication version 1.5.0
[INFO] Connected new brain: SoccerTwos?team=1
Connected new brain: SoccerTwos?team=1
[INFO] Connected new brain: SoccerTwos?team=0
Connected new brain: SoccerTwos?team=0
Initialize environment successful.
ＯＯ ＯＯＯＯＯ
ＯＯＯＯ ＯＯＯＯ ＯＯ ＯＯＯＯＯＯＯＯ ＯＯＯＯＯＯＯＯ ＯＯＯＯＯＯＯ ＯＯＯＯＯＯＯ
ＯＯＯ ＯＯＯ ＯＯＯＯ ＯＯ ＯＯＯ ＯＯ ＯＯＯ ＯＯ ＯＯ ＯＯＯ Ｏ
ＯＯＯ ＯＯＯＯ ＯＯＯＯ ＯＯ ＯＯＯ ＯＯ ＯＯＯ ＯＯ ＯＯ ＯＯＯ
ＯＯＯＯＯＯＯＯ Ｏ ＯＯ ＯＯ ＯＯ ＯＯ ＯＯ ＯＯＯＯＯＯ ＯＯＯ ＯＯＯ
Ｏ ＯＯＯ ＯＯ ＯＯＯＯＯＯ ＯＯ ＯＯ ＯＯ ＯＯ ＯＯ ＯＯＯ ＯＯ
Ｏ ＯＯＯ ＯＯ ＯＯ ＯＯ ＯＯ ＯＯＯ ＯＯ ＯＯＯ ＯＯ ＯＯＯ ＯＯ
ＯＯＯＯＯ ＯＯＯ ＯＯ ＯＯＯ ＯＯＯＯＯＯＯ ＯＯＯＯＯＯＯ ＯＯＯ ＯＯＯＯＯＯＯ
ＯＯＯＯ Ｏ ＯＯＯ ＯＯ ＯＯＯ ＯＯＯＯＯＯＯ ＯＯＯＯＯＯＯ ＯＯＯＯ ＯＯＯＯ
Initialize Agent Begin.
PyTorch Tensor Device: cpu
Initialize Agent Successfully.
Pre-filling: 38%|█████████████▌ | 3760/10000 [00:01<00:02]
index 16 is out of bounds for axis 0 with size 16
首先，我的实验环境就是ml-agents18官方提供的SoccerTwos，没有任何改动。另外，上述index 16 is out of bounds for axis 0 with size 16的错误在用导出环境中训练会出现，如果是直接在unity editor编辑器里start的话，会报相似但不完全相同的错误：index 18 is out of bounds for axis 0 with size 16（注意：16变成了18）